Persistent memory and RAG for AI coding agents. Episodic memories with decay + durable concept graphs. MCP server + CLI. Rust.
Conversation knowledge extraction and reconciliation for multi-LLM development workflows
Indexed semantic & BM25 code search for AI agents. Give your AI instant memory of your codebase. Rust | MCP Server.
Local document indexer MCP server for semantic search over PDF, Excel, SQL, Markdown, and HTML files using Qdrant and Voyage AI embeddings.
Open-source, self-hosted team memory for AI coding agents. Share, search, and audit project context through MCP.
Parallax - an MCP server of independent correctives for a model's predictable failure modes: adversarial verification, deterministic checks (Z3/evalexpr), verified cross-session memory, cited research
a mcp server for interacting with ChromaDB
A minimal Rust vector-memory server that works with Qdrant and Ollama.
A practical repository focused on mastering Spring AI concepts through hands-on implementations including RAG pipelines, vector search, AI agents, tool calling, memory handling, MCP servers, embedding
Apple ecosystem MCP server for Claude Code, Cursor, and other AI assistants — Notes, Reminders, Contacts with BERT semantic search
Stable MCP supervisor proxy for stdio servers: cached discovery, unified mcp.wrapper lifecycle control, and on-demand backend processes.
A high-performance Model Context Protocol (MCP) server written in Rust that extends AI models into autonomous coding agents with semantic memory, built-in Git tools, and codebase indexers
Long-term memory for coding agents over MCP: hybrid search over Markdown notes with a link graph, on PostgreSQL, Qdrant, and Ollama
Best Token-Efficient AI Coding Tools 2026 – Reduce Costs 90% with Local Memory & MCP
Serveur MCP pour bases de connaissance markdown versionnées en git. Des sessions Claude isolées les lisent et y déposent des propositions ; seul le rôle gestionnaire intègre.
Layered, self-learning knowledge base for teams, served over the Model Context Protocol. PostgreSQL + pgvector hybrid search, roles, audit log, YAML layer presets.
CodeNinja Atoms: a sovereign AI operating system for the physical world. Open reference architectures for physical AI, with ontologies, model registers, costs and DOIs. CC BY 4.0.
ExpHub is an open-source MCP server that transforms AI assistants into collaborative knowledge workers. It automatically searches past experiences, captures new solutions in structured templates, and
MCP server for searching, indexing, and retrieving scientific papers across arXiv, INSPIRE-HEP, Semantic Scholar, OpenAlex, CrossRef, NASA ADS, Europe PMC, DOAJ, and viXra. Local hybrid search with BM
Local-first semantic-search MCP server over a personal CS/FP/graphics library
(BACKEND )An MCP-compatible vector search server built in Go, powered by Pinecone and OpenAI.
CogniMem is a local MCP server in Rust that gives coding agents a persistent cognitive memory layer.
Semantic code-search MCP server for AI coding agents: hybrid retrieval (embeddings + BM25 + reranking), tree-sitter AST chunking, 30-100x fewer tokens
Personal knowledge system — MCP server with PostgreSQL semantic search and temporal knowledge graph
Cross-session persistent memory MCP server for AI assistants — local SQLite + FTS5, zero external dependencies
Persistent semantic memory service and MCP adapter for AI agents, powered by PostgreSQL and local Ollama models.
A simple Memory MCP server written in Rust
Session Memory MCP server for ADK-Rust Enterprise — typed session state, scoped memory, replay snapshots, resumable workflows
Shared, encrypted, verifiable team memory for coding agents (MCP server)
MCP (Model Context Protocol) Server for Retrieval Augmented Generation using Mongo and Gemini, OpenAI, with A2A support Grok
Model Context Protocol (MCP) server for FalkorDB — read-only graph access for AI assistants
An MCP server to build knowledge graph of OWL ontologies
Rust MCP server for HaloPSA - ticket management, workflow actions, and semantic search via the Model Context Protocol
MCP server to allow agents to learn from my personal knowledge management system.
A production-grade AI agent framework — Go MCP servers, 50+ skills, structured role workflows, and hybrid semantic search.
Company context and memory for agents: typed ontology knowledge graph with cited answers
Gesamtes Verzeichnis
RAG, Graphen und Langzeitgedächtnis für Agenten. 2,590 Server, die meistgenutzten zuerst. Jeder öffnet die Seite des Herausgebers.